© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20867
    Prev
    Next
    INDEX
    Explanations

    asterisk emphasis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     “
    -1.59
    of
    -1.54
    ly
    -1.50
    h
    -1.48
    c
    -1.48
    m
    -1.47
     inaweza
    -1.46
    ).
    -1.46
     decorativo
    -1.45
    话说
    -1.44
    POSITIVE LOGITS
     they
    1.85
    側に
    1.76
    natured
    1.59
    姻
    1.53
    ཌ
    1.52
    bandcamp
    1.51
     soirée
    1.51
    了出来
    1.50
    rée
    1.49
     Geografía
    1.48
    Activations Density 0.014%

    No Known Activations